Skip to content

Conversation

@altanh
Copy link
Contributor

@altanh altanh commented Jun 29, 2022

adds support for any shape and axis for log_softmax (this was already supported by regular softmax)

there's slight code duplication but it was a lot messier when I tried to reuse the softmax_common code in-place

cc @shingjan @masahi

@github-actions github-actions bot requested a review from masahi June 29, 2022 21:01
Copy link

@shingjan shingjan left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM. Thanks @altanh this is a life saver!

Returns
-------
output : tvm.te.Tensor
2-D output with same shape

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

nit: change this to "N-D" as well

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@shingjan Can you follow up this in your PR?

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

will do! Thanks

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@masahi This typo is fixed in #11978

@masahi masahi merged commit 898946f into apache:main Jun 30, 2022
blackkker pushed a commit to blackkker/tvm that referenced this pull request Jul 7, 2022
masahi pushed a commit to masahi/tvm that referenced this pull request Jul 15, 2022
mikeseven pushed a commit to mikeseven/tvm that referenced this pull request Sep 27, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants